Postdoctoral Fellow, AI/ML & Computational Immunology
Pfizer
8 hours ago
Remote friendly (Cambridge, MA)
United States
Clinical Research and Development
Responsibilities:
- Design and build ML models to detect, deconvolve, and interpret efferocytosis events from scRNA-seq and spatial omics (recovering mixed host/cargo transcriptomes).
- Generate/curate training & validation datasets (cross-species, multi-omic) and establish benchmarking and quality metrics.
- Develop reproducible end-to-end analysis toolkits/pipelines (ingestion, training, inference, interpretability, reporting).
- Link model outputs to biology (macrophage state transitions, pathway activation, disease phenotypes).
- Use interpretable ML to nominate/prioritize therapeutic targets and hypotheses for experimental follow-up.
- Collaborate with wet-lab/translational partners to validate and iterate; communicate insights via presentations and peer-reviewed manuscripts.
Qualifications (Minimum Requirements):
- Ph.D. (or thesis defense within 2–3 months) in computational biology/bioinformatics/CS/statistics/biomedical engineering/immunology (quantitative focus) or related.
- Willingness for minimum 2-year commitment; <2 years post-doctoral experience.
- Two letters of recommendation; at least one first-author scientific research article.
- Single-cell RNA-seq experience (preprocessing/QC/integration/annotation).
- Proficiency in Python and/or R; ability to write maintainable, well-tested code.
- ML experience (deep learning/representation learning; evaluation/benchmarking); HPC/cloud and reproducible workflows.
- Strong scientific writing/presentation skills; cross-disciplinary collaboration.
Preferred Skills:
- Spatial transcriptomics/omics; deep learning architectures (transformers/VAEs/GNNs), multi-task learning.
- Interpretability (feature attribution/perturbation) and/or causal inference; inflammation/fibrosis domain knowledge.
- Multi-modal integration/toolkit building (e.g., RNA+ATAC, protein, imaging).
- Experience with omics tools (Seurat/Scanpy/Squidpy, enrichment/network analysis) and wet-lab protocols for high-dimensional sc/nRNA-seq.
Benefits (explicitly stated):
- Base salary: $64,600–$107,600; bonus target 7.5% of base; 401(k) matching; paid vacation/holidays; caregiver/parental & medical leave; medical/dental/vision coverage.
- Design and build ML models to detect, deconvolve, and interpret efferocytosis events from scRNA-seq and spatial omics (recovering mixed host/cargo transcriptomes).
- Generate/curate training & validation datasets (cross-species, multi-omic) and establish benchmarking and quality metrics.
- Develop reproducible end-to-end analysis toolkits/pipelines (ingestion, training, inference, interpretability, reporting).
- Link model outputs to biology (macrophage state transitions, pathway activation, disease phenotypes).
- Use interpretable ML to nominate/prioritize therapeutic targets and hypotheses for experimental follow-up.
- Collaborate with wet-lab/translational partners to validate and iterate; communicate insights via presentations and peer-reviewed manuscripts.
Qualifications (Minimum Requirements):
- Ph.D. (or thesis defense within 2–3 months) in computational biology/bioinformatics/CS/statistics/biomedical engineering/immunology (quantitative focus) or related.
- Willingness for minimum 2-year commitment; <2 years post-doctoral experience.
- Two letters of recommendation; at least one first-author scientific research article.
- Single-cell RNA-seq experience (preprocessing/QC/integration/annotation).
- Proficiency in Python and/or R; ability to write maintainable, well-tested code.
- ML experience (deep learning/representation learning; evaluation/benchmarking); HPC/cloud and reproducible workflows.
- Strong scientific writing/presentation skills; cross-disciplinary collaboration.
Preferred Skills:
- Spatial transcriptomics/omics; deep learning architectures (transformers/VAEs/GNNs), multi-task learning.
- Interpretability (feature attribution/perturbation) and/or causal inference; inflammation/fibrosis domain knowledge.
- Multi-modal integration/toolkit building (e.g., RNA+ATAC, protein, imaging).
- Experience with omics tools (Seurat/Scanpy/Squidpy, enrichment/network analysis) and wet-lab protocols for high-dimensional sc/nRNA-seq.
Benefits (explicitly stated):
- Base salary: $64,600–$107,600; bonus target 7.5% of base; 401(k) matching; paid vacation/holidays; caregiver/parental & medical leave; medical/dental/vision coverage.